CN107133670A - A kind of Complex lithologic identification method and system based on decision tree data mining algorithm - Google Patents
A kind of Complex lithologic identification method and system based on decision tree data mining algorithm Download PDFInfo
- Publication number
- CN107133670A CN107133670A CN201710266077.7A CN201710266077A CN107133670A CN 107133670 A CN107133670 A CN 107133670A CN 201710266077 A CN201710266077 A CN 201710266077A CN 107133670 A CN107133670 A CN 107133670A
- Authority
- CN
- China
- Prior art keywords
- lithology
- data set
- data
- decision tree
- complex
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003066 decision tree Methods 0.000 title claims abstract description 53
- 238000007418 data mining Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000005553 drilling Methods 0.000 claims abstract description 13
- 238000007789 sealing Methods 0.000 claims abstract description 13
- 230000004044 response Effects 0.000 claims description 14
- 239000011435 rock Substances 0.000 claims description 12
- 238000005498 polishing Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000013480 data collection Methods 0.000 claims 1
- 230000015572 biosynthetic process Effects 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000013138 pruning Methods 0.000 description 15
- 230000009286 beneficial effect Effects 0.000 description 8
- 238000011160 research Methods 0.000 description 8
- 238000005266 casting Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 238000009412 basement excavation Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000007935 neutral effect Effects 0.000 description 3
- 239000003208 petroleum Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000004575 stone Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 241001269238 Data Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 229910052500 inorganic mineral Inorganic materials 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000011707 mineral Substances 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21B—EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B49/00—Testing the nature of borehole walls; Formation testing; Methods or apparatus for obtaining samples of soil or well fluids, specially adapted to earth drilling or wells
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geology (AREA)
- Mining & Mineral Resources (AREA)
- Artificial Intelligence (AREA)
- Geochemistry & Mineralogy (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Fluid Mechanics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Environmental & Geological Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of Complex lithologic identification method and system based on decision tree data mining algorithm.It is related to oil exploration reservoir assessment technology field.Methods described includes：The lithological profile of sealing core drilling well section is set up, Lithology Discrimination data set is formed according to lithological profile；Data prediction is carried out to the Lithology Discrimination data set；Correspond to the different lithology in Lithology Discrimination data set respectively with different log parameters；Data mining is carried out to the lithology in the Lithology Discrimination data set after pretreatment, tree-shaped identification model is formed, so that complex lithology is identified the lithology according to corresponding to the tree-shaped identification model and log parameter.The present invention passes through lithological profile formation Lithology Discrimination data set, carry out unified Lithology Discrimination, and different log parameters are corresponded to according to the characteristics of lithology, after data mining is carried out to Lithology Discrimination data set, clear tree-shaped identification model is formed, accurate Lithology Discrimination can be carried out under complex lithology situation.
Description
Technical field
Decision tree data mining algorithm is based on the present invention relates to oil exploration reservoir assessment technology field, more particularly to one kind
Complex lithologic identification method and system.
Background technology
With the expansion of petroleum exploration and development breadth and depth, one side oil data are constantly accumulated with very fast speed,
If the oil data of magnanimity are made full use of as a kind of carrier of wealth, it can be brought additionally to Petroleum finance
Benefit, traditional geophysical exploration method theoretical based on petrophysics, mathematics, statistics, oil exploration for
In-depth seems that some are helpless using these mass datas；On the other hand various untraditional reservoirs are just turning into main force's exploration pair
As for these complex reservoirs, the method such as conventional cross plot, linear regression, multivariate discriminant analysis can not be solved effectively
Certainly Lithology Discrimination, reservoir parameter calculate etc. problem.Therefore, be necessary in petroleum exploration and development introduce artificial intelligence, machine learning,
The new method of other research fields such as pattern-recognition, data mining, can be fine as the solution of a kind of " data-driven "
Ground solves the various problems run into complex reservoir evaluation.
Data mining be exactly it is implicit from substantial amounts of, incomplete, noisy, fuzzy, random extracting data,
Process that is unknown in advance but being potentially useful information and knowledge.Data mining task is divided into two major classes of description and prediction, preceding
The summary pattern of potential relation in person's export data, the latter is inferred that, to make prediction, main method has god to current data
Through network, SVMs, Bayesian network and decision tree etc., wherein neutral net oneself through being widely used in Lithology Discrimination, it is heavy
Product is mutually in terms of division, Permeability Prediction, oil-gas-water layer identification, in practice it has proved that, when the complicated oil of processing many factors influence
During geological problem, nonlinear neural net method is more superior than linear statistical analysis technique.But neutral net has most
Big shortcoming is exactly that easily training sample " is crossed and learnt ", and the variable element of method is too many, if giving algorithm time enough, it
Anything " can be almost remembered ", the model being built such that will depart from geologic setting, without actual application value；Separately
Outside, neutral net, SVMs and Bayesian network also have one common disadvantage is that prediction model belong to it is " black
Box ", can't see with relation fitting in what manner between sample data and attribute.
The content of the invention
In order to solve the above-mentioned technical problem there is provided a kind of complex lithology knowledge based on decision tree data mining algorithm by the present invention
Other method and system.
The technical scheme that the present invention solves above-mentioned technical problem is as follows：A kind of complexity based on decision tree data mining algorithm
Lithology Identification Methods, methods described includes：
The lithological profile of sealing core drilling well section is set up, Lithology Discrimination data set is formed according to lithological profile；
Data prediction is carried out to the Lithology Discrimination data set；
Correspond to the different lithology in Lithology Discrimination data set respectively with different log parameters；
Data mining is carried out to the lithology in the Lithology Discrimination data set after pretreatment, tree-shaped identification model is formed, from
And complex lithology is identified the lithology according to corresponding to the tree-shaped identification model and log parameter.
The beneficial effects of the invention are as follows：The present invention carries out unified lithology by lithological profile formation Lithology Discrimination data set
Identification, and the different log parameter of correspondence according to the characteristics of lithology, after data mining is carried out to Lithology Discrimination data set, are formed
Clear tree-shaped identification model, can carry out accurate Lithology Discrimination under complex lithology situation.
On the basis of above-mentioned technical proposal, the present invention can also do following improvement.
Further, after the lithological profile of sealing core drilling well section is set up, the survey according to thick-layer, short lap and lithology intermediate zone
Well readings principle reads the log response of different lithology section respectively, sets up conglomerate lithology pass corresponding with log parameter
System, forms Lithology Discrimination data set.
Further, the process of data prediction is carried out to the Lithology Discrimination data set includes polishing missing values, overall mark
Standardization and elimination abnormity point.
Beneficial effect using above-mentioned further scheme is：The shadow of log response in the presence of short lap and lithology intermediate zone
Sound can all cause data exception, accordingly, it would be desirable to which abnormity point is eliminated so as to precisely identification.
Further, data digging is carried out to the lithology in the Lithology Discrimination data set after pretreatment using decision Tree algorithms
Pick.
Beneficial effect using above-mentioned further scheme is：Decision Tree algorithms belong to " whitepack " and seal model up for safekeeping, can understand
Recognize grader be how to work and log parameter importance.For anisotropism is serious, complex lithology is changeable
Oil and gas reservoir, traditional mathematical statistics method is difficult to reflect exactly the Nonlinear Mapping relation between log and lithology,
And the traditional decision-tree with self-organizing, self study, reasoned thinking ability and Nonlinear Modeling can solve this well and ask
Topic, provides high-precision Lithology Discrimination result, it is ensured that the reasonable Efficient Development of complex reservoir for evaluating reservoir.
Further, it is to the process that the lithology in the Lithology Discrimination data set after pretreatment carries out data mining：Calculate
Go out weight of each log parameter in Lithology Discrimination, obtain sensitive parameter and be modeled, characteristic manner with from top to bottom finally
Tree-shaped identification model is set up, wherein each branch set represents the recognition rule of a class lithology, leaf node represents to constitute the knowledge
Not other numerical intervals of regular log parameter and each log parameter.
Beneficial effect using above-mentioned further scheme is：Analyzed by the weight to different log parameters and then oneself
Dynamic preferably to go out lithology sensitive parameter, final set up takes into account Model Identification precision and the Complex lithologic identification mould of sample generalization ability
Type, important geologic basis is provided for Comprehensive Evaluation of Reservoir.
In order to solve the above-mentioned technical problem, the present invention also proposes a kind of complex lithology based on decision tree data mining algorithm
Identifying system, the system includes：
Data set sets up module, the lithological profile for setting up sealing core drilling well section, and forming lithology according to lithological profile knows
Other data set；
Pretreatment module, for carrying out data prediction to the Lithology Discrimination data set；
Mark module, for corresponding to the different lithology in Lithology Discrimination data set respectively with different log parameters；
Data-mining module, for carrying out data mining, shape to the lithology in the Lithology Discrimination data set after pretreatment
Into tree-shaped identification model, so that the lithology according to corresponding to the tree-shaped identification model and log parameter is carried out to complex lithology
Identification.
The beneficial effects of the invention are as follows：The present invention carries out unified lithology by lithological profile formation Lithology Discrimination data set
Identification, and the different log parameter of correspondence according to the characteristics of lithology, after data mining is carried out to Lithology Discrimination data set, are formed
Clear tree-shaped identification model, can carry out accurate Lithology Discrimination under complex lithology situation.
Further, the data set is set up module and is additionally operable to after the lithological profile of sealing core drilling well section is set up, according to thick
The well logging readings principle of layer, short lap and lithology intermediate zone reads the log response of different lithology section respectively, sets up gravel
The corresponding relation of rock lithology and log parameter, forms Lithology Discrimination data set.
Further, the pretreatment module to the Lithology Discrimination data set specifically for carrying out polishing missing values, entirety
Standardization and the pretreatment for eliminating abnormity point.
Beneficial effect using above-mentioned further scheme is：The shadow of log response in the presence of short lap and lithology intermediate zone
Sound can all cause data exception, accordingly, it would be desirable to which abnormity point is eliminated so as to precisely identification.
Further, the data-mining module is specifically for using decision Tree algorithms to the Lithology Discrimination number after pretreatment
Data mining is carried out according to the lithology of concentration.
Beneficial effect using above-mentioned further scheme is：Decision Tree algorithms belong to " whitepack " and seal model up for safekeeping, can understand
Recognize grader be how to work and log parameter importance.For anisotropism is serious, complex lithology is changeable
Oil and gas reservoir, traditional mathematical statistics method is difficult to reflect exactly the Nonlinear Mapping relation between log and lithology,
And the traditional decision-tree with self-organizing, self study, reasoned thinking ability and Nonlinear Modeling can solve this well and ask
Topic, provides high-precision Lithology Discrimination result, it is ensured that the reasonable Efficient Development of complex reservoir for evaluating reservoir.
Further, the data-mining module is additionally operable to calculate weight of each log parameter in Lithology Discrimination, obtains
Obtain sensitive parameter to be modeled, tree-shaped identification model is finally set up from top to bottom with characteristic manner, wherein each branch set
The recognition rule of a class lithology is represented, leaf node represents to constitute the log parameter of the recognition rule and the number of each log parameter
Value is interval.
Beneficial effect using above-mentioned further scheme is：Analyzed by the weight to different log parameters and then oneself
Dynamic preferably to go out lithology sensitive parameter, final set up takes into account Model Identification precision and the Complex lithologic identification mould of sample generalization ability
Type, important geologic basis is provided for Comprehensive Evaluation of Reservoir.
Brief description of the drawings
Fig. 1 is the flow chart of the Complex lithologic identification method described in the embodiment of the present invention；
Fig. 2 is the tree-shaped identification model schematic diagram described in the embodiment of the present invention；
Fig. 3 is the schematic diagram of the Complex lithologic identification system described in the embodiment of the present invention.
Embodiment
The principle and feature of the present invention are described below in conjunction with accompanying drawing, the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the present invention.
As shown in figure 1, the present embodiment sets up high-precision, non-to determine the response relation of different lithology and log
Linear Lithology Discrimination model, improves the accuracy of identification of complex lithology, proposes a kind of answering based on decision tree data mining algorithm
Miscellaneous Lithology Identification Methods, methods described includes：
The lithological profile of sealing core drilling well section is set up, Lithology Discrimination data set is formed according to lithological profile；
Data prediction is carried out to the Lithology Discrimination data set；
Correspond to the different lithology in Lithology Discrimination data set respectively with different log parameters；
Data mining is carried out to the lithology in the Lithology Discrimination data set after pretreatment, tree-shaped identification model is formed, from
And complex lithology is identified the lithology according to corresponding to the tree-shaped identification model and log parameter.
It is preferred that, before Lithology Discrimination data set is formed, the geologic setting and reservoir characteristics in binding area, based on storage
Layer evaluates overall requirement, describes to name the lithology for determining research area in terms of two with casting body flake from the core sample of sealed coring well
Title, because the anisotropism of complicated reservoirs is strong, acutely, the local casting body flake of rock core can not accurately reflect stratum to variation of lithological
True lithology；And core description lacks the quantitative scale to different minerals composition, effective combination of two methods can be carried
The accuracy rate that high complex lithology is named.
By taking the following group Conglomerate Reservoir in area gram in Karamay oilfield six as an example, Conglomerate Reservoir is due to golden material resource, many water systems and fast
The depositional environment of speed change causes reservoir heterogeneity strong and the features such as changeable complex lithology, and lithology is accurately identified as such
The difficult point of oil reservoir adjustment exploitation.Core sample description and casting body flake qualification result according to research 8 mouthfuls of area sealed coring well is true
Determine the lithology of Conglomerate Reservoir mainly include conglomerate, glutenite, chiltern conglomerate, containing glutenite, gritstone containing gravel, pebbly sandstone, in
Several lithology of sandstone, packsand, pebbly mudstone, silty, mud stone etc. ten.
Specifically, using sequence stratigraphy as according to the lithological profile for setting up 8 mouthfuls of sealing core drilling well sections, reading different lithology section
Log response, the conglomerate lithology of 327 intervals and the corresponding relation of log data are set up altogether, conglomerate lithology is formed
The sample data set of identification.
Wherein, the principle of well logging readings is as follows：1. thick-layer reads average value as the basic data of Lithology Discrimination；2. mud
The maximum or minimum value that the short laps such as rock, glutenite, volcanic rock, metamorphic rock read log are used as the basis of Lithology Discrimination
Data；3. the intermediate zone between different lithology reads average value, or carries out back-up processing as abnormity point in data prediction.
Data prediction is carried out for the Lithology Discrimination sample data set of foundation, mainly includes polishing missing values, overall mark
Standardization, eliminates abnormity point etc., most important of which preprocessor is the deletion of abnormity point, for the storage with complex lithology
Layer, the reason for causing data sample abnormal mainly has two aspects, and one is the presence of short lap, due to logger longitudinal frame
Limitation, log response value can not reflect the real information of formation lithology；On the other hand due to log response in lithology intermediate zone
Influenceed by both sides country rock, well logging numerical value also is difficult to the information of the true lithology of accurate calibration.Lost according to log value is caused
Genuine reason, deletes 18 abnormal point numericals, it is caused mainly due to short lap and lithology intermediate zone altogether.
The complex lithology classification for determining to need to recognize is named based on lithology, can be to some phases according to the requirement of evaluating reservoir
Merge, some important lithology can also be finely divided like lithology；In addition, determining the excavation field of decision Tree algorithms, i.e.,
Which log is selected to indicate lithological information.
Specifically, according to the total demand of Conglomerate Reservoir evaluating reservoir, area gram the following group conglomerate lithology is ultimately determined in six
8 kinds of conglomerate, chiltern conglomerate, glutenite, gritstone containing gravel, packsand, pebbly mudstone, silty and mud stone etc.；Excavate word
Section selection virgin zone resistivity (Rt), natural gamma (GR), natural potential (SP), hole diameter (CAL), neutron porosity (CNL),
Interval transit time (AC) and compensation density (DEN) amount to 7 log parameters to indicate lithology.
The present embodiment carries out data digging using decision Tree algorithms to the lithology in the Lithology Discrimination data set after pretreatment
Pick.
Specifically, decision Tree algorithms carry out the data mining of conglomerate lithology using C5.0, algorithm utilizes information gain-ratio
(Information Gain Ratio) is used as split vertexes as measurement, the maximum attribute of selection information gain-ratio value is divided；
The method that C5.0 uses errors of pessimism beta pruning (Pessimistic Error Pruning), that is, utilize the company in binomial distribution
Continuous amendment is corrected to substituting into error again, more to be met actual error rate.
How the selection of Split Attribute selects an optimal Split Attribute from numerous attributes, is the core of algorithm,
Selection standard is roughly divided into two classes：1. selection strategy separate between attribute；2. be mutually related selection strategy between attribute, often
The method of kind has its advantage and disadvantage, is carried out based on actual sample data preferred.Pruning strategy includes predictive pruning and the class of rear beta pruning two, preceding
Person increases tactful using tree is stopped early；The latter is then to be first according to maximum-norm generation initial decision tree, is then cut again
Branch, in practice it has proved that rear pruning method is more successful for Oil/Gas Reservoir Assessment field.
On the basis of Split Attribute and Pruning strategy are determined, Lithology Discrimination data set of the decision Tree algorithms to foundation is utilized
Excavated, decision Tree algorithms can provide weight of each log parameter in Lithology Discrimination, and then preferably go out sensitive parameter
It is modeled, smaller for shared weight, the relatively low parameter of sensitiveness is then not involved in the foundation of decision-tree model.It is determined that modeling
After sensitive parameter, decision Tree algorithms " are divided and rule " from top to down sets up tree-shaped identification model, and each branch of tree represents one
The recognition rule of class lithology, leaf node represents to constitute the property parameters of the recognition rule and the numerical intervals of each parameter.
Specifically, from 73 conglomerate lithology sensitive parameters preferably gone out in excavating field, the ginseng of virgin zone resistivity
Number weight is maximum, sensitiveness highest；Interval transit time and natural gamma take second place, and other 4 parameters are due in conglomerate Lithology Discrimination
Shared weight is smaller, and sensitiveness is relatively low, thus is not involved in the foundation of decision-tree model.On the preferred basis of lithology sensitive parameter
On, decision Tree algorithms set up tree-shaped identification model, and Lithology Discrimination model is since root node is virgin zone resistivity on the whole
Data sample is tested, " dividing and rule " to amount to from top to down is divided into four levels, and each branch of tree represents a class rock
The recognition rule of property, as shown in Figure 2.
" the branch rule " set up using decision tree can recognize the lithology that sample data is concentrated exactly, conglomerate lithology
Sample data amounts to 309, and decision-tree model can accurately identify 296, and comprehensive recognition accuracy reaches 95.79%.Due to
What is set up is high accuracy, nonlinear identification model, and compared to conventional intersection drawing method, accuracy of identification is increased substantially.Separately
Outside, generalization ability of the model on other data sets is also relatively good, may apply to the Complex lithologic identification of research other wells of area
In.
Decision tree data mining algorithm preferably goes out the sensitive parameter of conglomerate Lithology Discrimination according to given excavation field automatically,
And then the tree-shaped identification model of Nonlinear Mapping is set up, the synthesis recognition accuracy of model is higher.In order to geophysics
Family provides identification model that is more directly perceived, being more easy to application, in three conglomerate lithology sensitive parameters that algorithm preferably goes out, constructs first
Interval transit time and the product of natural gamma (AC*GR), conglomerate lithology cross plot is made then in conjunction with virgin zone resistivity (Rt)
Version, the change information according to crossplot analyzes the changing rule of reservoir, and it is strong to be that the adjustment of Conglomerate Reservoir development plan and keeping away is penetrated
Water Flooding Layer provides geologic basis.
The complex lithology for the Lithology Discrimination model evaluation Conglomerate Reservoirs, Karamay Oil Field set up using this example, is achieved
Relatively good Effect of geological application, and provide a kind of new resolving ideas and scheme for the evaluating reservoir of complex reservoir.
From the example of Conglomerate Reservoir Lithology Discrimination as can be seen that data mining can in a large amount of unknown data Automatic-searching lithology
Sensitive parameter, nonlinear decision tree identification model is set up by the analysis to parameters weighting, and the process of data mining and knot
Research of the fruit to set up lithology plate using geophysics knowledge provides idea and method.Two methods be interdepend, phase
The relation mutually promoted, data mining can give people to provide the analysis of law of some mass datas in early stage, help geophysics
Useful information is extracted in research；Geophysicist selects some important information using its background knowledge and to construct some new
Parameter, can help data digging method determine more rationally and it is effective excavate field, be the foundation of geophysical model
Accuracy, quantification, the result of sectionalization are provided.
As shown in figure 3, corresponding, the present embodiment also proposes that a kind of complex lithology based on decision tree data mining algorithm is known
Other system, the system includes：
Data set sets up module, the lithological profile for setting up sealing core drilling well section, and forming lithology according to lithological profile knows
Other data set；
Pretreatment module, for carrying out data prediction to the Lithology Discrimination data set；
Mark module, for corresponding to the different lithology in Lithology Discrimination data set respectively with different log parameters；
Data-mining module, for carrying out data mining, shape to the lithology in the Lithology Discrimination data set after pretreatment
Into tree-shaped identification model, so that the lithology according to corresponding to the tree-shaped identification model and log parameter is carried out to complex lithology
Identification.
Before Lithology Discrimination data set is formed, the geologic setting and reservoir characteristics in binding area, based on evaluating reservoir
It is overall to require, the lithology title in determination research area in terms of two is named from core sample description and the casting body flake of sealed coring well,
Because the anisotropism of complicated reservoirs is strong, acutely, the local casting body flake of rock core can not accurately reflect the true of stratum to variation of lithological
Real lithology；And core description lacks the quantitative scale to different minerals composition, effective combination of two methods can improve multiple
The accuracy rate that complex is named.
On the basis of lithology is named, using sequence stratigraphy as according to the lithological profile for setting up sealing core drilling well section, read
The log response of different lithology section, the principle for readings of logging well is as follows：1. thick-layer reads average value and is used as Lithology Discrimination
Basic data；2. the short lap such as mud stone, glutenite, volcanic rock, metamorphic rock reads maximum or the minimum value conduct of log
The basic data of Lithology Discrimination；3. the intermediate zone between different lithology reads average value, or as abnormal in data prediction
Point carries out back-up processing.
Data prediction is carried out for the Lithology Discrimination sample data set of foundation, mainly includes polishing missing values, overall mark
Standardization, eliminates abnormity point etc., most important of which preprocessor is the deletion of abnormity point, for the storage with complex lithology
Layer, the reason for causing data sample abnormal mainly has two aspects, and one is the presence of short lap, due to logger longitudinal frame
Limitation, log response value can not reflect the real information of formation lithology；On the other hand due to log response in lithology intermediate zone
Influenceed by both sides country rock, well logging numerical value also is difficult to the information of the true lithology of accurate calibration.
The complex lithology classification for determining to need to recognize is named based on lithology, can be to some phases according to the requirement of evaluating reservoir
Merge, some important lithology can also be finely divided like lithology；In addition, determining the excavation field of decision Tree algorithms, i.e.,
Which log is selected to indicate lithological information.
The present embodiment carries out data digging using decision Tree algorithms to the lithology in the Lithology Discrimination data set after pretreatment
Pick.
Specifically, decision Tree algorithms carry out the data mining of conglomerate lithology using C5.0, algorithm utilizes information gain-ratio
(Information Gain Ratio) is used as split vertexes as measurement, the maximum attribute of selection information gain-ratio value is divided；
The method that C5.0 uses errors of pessimism beta pruning (Pessimistic Error Pruning), that is, utilize the company in binomial distribution
Continuous amendment is corrected to substituting into error again, more to be met actual error rate.
How the selection of Split Attribute selects an optimal Split Attribute from numerous attributes, is the core of algorithm,
Selection standard is roughly divided into two classes：1. selection strategy separate between attribute；2. be mutually related selection strategy between attribute, often
The method of kind has its advantage and disadvantage, is carried out based on actual sample data preferred.Pruning strategy includes predictive pruning and the class of rear beta pruning two, preceding
Person increases tactful using tree is stopped early；The latter is then to be first according to maximum-norm generation initial decision tree, is then cut again
Branch, in practice it has proved that rear pruning method is more successful for Oil/Gas Reservoir Assessment field.
On the basis of Split Attribute and Pruning strategy are determined, Lithology Discrimination data set of the decision Tree algorithms to foundation is utilized
Excavated, decision Tree algorithms can provide weight of each log parameter in Lithology Discrimination, and then preferably go out sensitive parameter
It is modeled, smaller for shared weight, the relatively low parameter of sensitiveness is then not involved in the foundation of decision-tree model.It is determined that modeling
After sensitive parameter, decision Tree algorithms " are divided and rule " from top to down sets up tree-shaped identification model, and each branch of tree represents one
The recognition rule of class lithology, leaf node represents to constitute the property parameters of the recognition rule and the numerical intervals of each parameter.
Complex lithologic identification method of the present invention based on decision tree data mining algorithm, its core technology is division
Property value and Pruning strategy it is preferred, algorithm determines every kind of survey by the comprehensive analysis to different lithology and log response
Weight of the well curve in Lithology Discrimination, and then preferably go out lithology sensitive parameter and set up tree shaped model, the precision of model and extensive
Ability is all relatively good.Relative to cross plot and other data mining algorithms, decision tree Lithology Identification Methods can provide high accuracy,
Nonlinear identification model, for the evaluating reservoir with complex lithology, its accuracy of identification is higher than common cross-plot；It is another
Aspect, decision Tree algorithms belong to " whitepack " and seal model up for safekeeping, and can be understood that grader is how to work and each seed ginseng
Several relative importances, also has good directive function to geophysical research.Therefore, storage of the invention in complex lithology
Layer has important application value and the preferable market demand in evaluating.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc. should be included in the scope of the protection.
Claims (10)
1. a kind of Complex lithologic identification method based on decision tree data mining algorithm, it is characterised in that methods described includes：
The lithological profile of sealing core drilling well section is set up, Lithology Discrimination data set is formed according to lithological profile；
Data prediction is carried out to the Lithology Discrimination data set；
Correspond to the different lithology in Lithology Discrimination data set respectively with different log parameters；
Data mining is carried out to the lithology in the Lithology Discrimination data set after pretreatment, tree-shaped identification model is formed, so that root
Complex lithology is identified according to the lithology corresponding to the tree-shaped identification model and log parameter.
2. a kind of Complex lithologic identification method based on decision tree data mining algorithm according to claim 1, its feature
It is, after the lithological profile of sealing core drilling well section is set up, the well logging readings principle according to thick-layer, short lap and lithology intermediate zone
The log response of different lithology section is read respectively, the corresponding relation of conglomerate lithology and log parameter is set up, and forms lithology
Identification data collection.
3. a kind of Complex lithologic identification method based on decision tree data mining algorithm according to claim 2, its feature
It is, the process that data prediction is carried out to the Lithology Discrimination data set is standardized and disappeared including polishing missing values, entirety
Except abnormity point.
4. a kind of Complex lithologic identification method based on decision tree data mining algorithm according to claim 3, its feature
It is, data mining is carried out to the lithology in the Lithology Discrimination data set after pretreatment using decision Tree algorithms.
5. a kind of Complex lithologic identification side based on decision tree data mining algorithm according to any one of Claims 1-4
Method, it is characterised in that be to the process that the lithology in the Lithology Discrimination data set after pretreatment carries out data mining：Calculate
Each weight of the log parameter in Lithology Discrimination, is obtained sensitive parameter and is modeled, finally built from top to bottom with characteristic manner
Tree-shaped identification model is found, wherein each branch set represents the recognition rule of a class lithology, leaf node represents to constitute the identification
The log parameter of rule and the numerical intervals of each log parameter.
6. a kind of Complex lithologic identification system based on decision tree data mining algorithm, it is characterised in that the system includes：
Data set sets up module, the lithological profile for setting up sealing core drilling well section, and Lithology Discrimination number is formed according to lithological profile
According to collection；
Pretreatment module, for carrying out data prediction to the Lithology Discrimination data set；
Mark module, for corresponding to the different lithology in Lithology Discrimination data set respectively with different log parameters；
Data-mining module, for carrying out data mining to the lithology in the Lithology Discrimination data set after pretreatment, forms tree
Shape identification model, so that the lithology according to corresponding to the tree-shaped identification model and log parameter is known to complex lithology
Not.
7. a kind of Complex lithologic identification system based on decision tree data mining algorithm according to claim 6, its feature
Be, the data set is set up module and is additionally operable to after the lithological profile of sealing core drilling well section is set up, according to thick-layer, short lap and
The well logging readings principle of lithology intermediate zone reads the log response of different lithology section respectively, sets up conglomerate lithology and well logging
The corresponding relation of parameter, forms Lithology Discrimination data set.
8. a kind of Complex lithologic identification system based on decision tree data mining algorithm according to claim 7, its feature
Be, the pretreatment module specifically for the Lithology Discrimination data set is carried out polishing missing values, overall standardization and
Eliminate the pretreatment of abnormity point.
9. a kind of Complex lithologic identification system based on decision tree data mining algorithm according to claim 8, its feature
It is, the data-mining module is specifically for using decision Tree algorithms to the rock in the Lithology Discrimination data set after pretreatment
Property carry out data mining.
10. a kind of Complex lithologic identification system based on decision tree data mining algorithm according to any one of claim 6 to 9
System, it is characterised in that the data-mining module is additionally operable to calculate weight of each log parameter in Lithology Discrimination, is obtained
Sensitive parameter is modeled, and finally sets up tree-shaped identification model from top to bottom with characteristic manner, wherein each the branch's generation set
The recognition rule of the class lithology of table one, leaf node represents to constitute the log parameter of the recognition rule and the numerical value of each log parameter
It is interval.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710266077.7A CN107133670A (en) | 2017-04-21 | 2017-04-21 | A kind of Complex lithologic identification method and system based on decision tree data mining algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710266077.7A CN107133670A (en) | 2017-04-21 | 2017-04-21 | A kind of Complex lithologic identification method and system based on decision tree data mining algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107133670A true CN107133670A (en) | 2017-09-05 |
Family
ID=59716483
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710266077.7A Pending CN107133670A (en) | 2017-04-21 | 2017-04-21 | A kind of Complex lithologic identification method and system based on decision tree data mining algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107133670A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109558615A (en) * | 2017-09-27 | 2019-04-02 | 中国石油化工股份有限公司 | Exploration decision making tree analysis method and system |
| CN109577972A (en) * | 2018-12-21 | 2019-04-05 | 西南石油大学 | Sandy gravel materials rock mechanics parameters Logging Evaluation Method based on lithology breakdown |
| CN109611087A (en) * | 2018-12-11 | 2019-04-12 | 中国石油大学(北京) | A kind of Volcanic Reservoir reservoir parameter intelligent Forecasting and system |
| WO2020082824A1 (en) * | 2018-10-25 | 2020-04-30 | 北京国双科技有限公司 | Model generation method and device and lithologic identification method and device |
| CN111489034A (en) * | 2020-04-10 | 2020-08-04 | 华中科技大学 | Construction method and application of oil and gas reservoir permeability prediction model |
| CN111561313A (en) * | 2020-05-15 | 2020-08-21 | 中国地质大学（北京） | Compact sandstone reservoir parameter prediction method based on physical model and machine learning |
| CN112505154A (en) * | 2020-11-11 | 2021-03-16 | 中国地质大学（北京） | Shale reservoir mineral component content analysis and lithofacies identification characterization method |
| CN112523740A (en) * | 2019-09-04 | 2021-03-19 | 中国石油天然气集团有限公司 | Rock type identification method and device for ultra-deep sea underground oil and gas exploration |
| CN112766309A (en) * | 2020-12-30 | 2021-05-07 | 中国地质调查局成都地质调查中心 | Lithology identification method and system |
| CN112930427A (en) * | 2018-09-28 | 2021-06-08 | 斯伦贝谢技术有限公司 | Elastic self-adaptive underground acquisition system |
| CN113073959A (en) * | 2021-02-24 | 2021-07-06 | 西南石油大学 | Drilling well loss mechanism prediction and auxiliary decision method based on fuzzy decision tree |
| US11947069B2 (en) | 2018-05-15 | 2024-04-02 | Schlumberger Technology Corporation | Adaptive downhole acquisition system |
-
2017
- 2017-04-21 CN CN201710266077.7A patent/CN107133670A/en active Pending
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109558615A (en) * | 2017-09-27 | 2019-04-02 | 中国石油化工股份有限公司 | Exploration decision making tree analysis method and system |
| CN109558615B (en) * | 2017-09-27 | 2021-09-14 | 中国石油化工股份有限公司 | Oil-gas exploration decision tree analysis method and system |
| US11947069B2 (en) | 2018-05-15 | 2024-04-02 | Schlumberger Technology Corporation | Adaptive downhole acquisition system |
| CN112930427B (en) * | 2018-09-28 | 2024-03-19 | 斯伦贝谢技术有限公司 | Elastic self-adaptive underground acquisition system |
| CN112930427A (en) * | 2018-09-28 | 2021-06-08 | 斯伦贝谢技术有限公司 | Elastic self-adaptive underground acquisition system |
| WO2020082824A1 (en) * | 2018-10-25 | 2020-04-30 | 北京国双科技有限公司 | Model generation method and device and lithologic identification method and device |
| CN111104819A (en) * | 2018-10-25 | 2020-05-05 | 北京国双科技有限公司 | Model generation method and device and lithology identification method and device |
| CN109611087A (en) * | 2018-12-11 | 2019-04-12 | 中国石油大学(北京) | A kind of Volcanic Reservoir reservoir parameter intelligent Forecasting and system |
| CN109611087B (en) * | 2018-12-11 | 2021-10-08 | 中国石油大学(北京) | Volcanic oil reservoir parameter intelligent prediction method and system |
| CN109577972B (en) * | 2018-12-21 | 2021-08-10 | 西南石油大学 | Glutenite reservoir rock mechanical parameter logging evaluation method based on lithology classification |
| CN109577972A (en) * | 2018-12-21 | 2019-04-05 | 西南石油大学 | Sandy gravel materials rock mechanics parameters Logging Evaluation Method based on lithology breakdown |
| CN112523740A (en) * | 2019-09-04 | 2021-03-19 | 中国石油天然气集团有限公司 | Rock type identification method and device for ultra-deep sea underground oil and gas exploration |
| CN111489034A (en) * | 2020-04-10 | 2020-08-04 | 华中科技大学 | Construction method and application of oil and gas reservoir permeability prediction model |
| CN111561313B (en) * | 2020-05-15 | 2020-12-11 | 中国地质大学（北京） | Compact sandstone reservoir parameter prediction method based on physical model and machine learning |
| CN111561313A (en) * | 2020-05-15 | 2020-08-21 | 中国地质大学（北京） | Compact sandstone reservoir parameter prediction method based on physical model and machine learning |
| CN112505154B (en) * | 2020-11-11 | 2021-06-29 | 中国地质大学（北京） | Shale reservoir mineral component content analysis and lithofacies identification characterization method |
| CN112505154A (en) * | 2020-11-11 | 2021-03-16 | 中国地质大学（北京） | Shale reservoir mineral component content analysis and lithofacies identification characterization method |
| CN112766309A (en) * | 2020-12-30 | 2021-05-07 | 中国地质调查局成都地质调查中心 | Lithology identification method and system |
| CN113073959A (en) * | 2021-02-24 | 2021-07-06 | 西南石油大学 | Drilling well loss mechanism prediction and auxiliary decision method based on fuzzy decision tree |
| CN113073959B (en) * | 2021-02-24 | 2022-04-08 | 西南石油大学 | Drilling well loss mechanism prediction and auxiliary decision method based on fuzzy decision tree |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107133670A (en) | A kind of Complex lithologic identification method and system based on decision tree data mining algorithm | |
| Wang et al. | Methodology of organic-rich shale lithofacies identification and prediction: A case study from Marcellus Shale in the Appalachian basin | |
| CN109061765B (en) | Trap evaluation method for heterogeneous thin sandstone interbed reservoir | |
| Yasin et al. | Estimation of petrophysical parameters from seismic inversion by combining particle swarm optimization and multilayer linear calculator | |
| Abdideh et al. | Cluster analysis of petrophysical and geological parameters for separating the electrofacies of a gas carbonate reservoir sequence | |
| Yarmohammadi et al. | Seismic reservoir characterization of a deep water sandstone reservoir using hydraulic and electrical flow units: a case study from the Shah Deniz gas field, the South Caspian Sea | |
| Kianoush et al. | Determining the drilling mud window by integration of geostatistics, intelligent, and conditional programming models in an oilfield of SW Iran | |
| Abeed et al. | Modeling of petrophysical properties and reserve estimation of Mishrif formation-Garraf oil field | |
| Alameedy et al. | Evaluating machine learning techniques for carbonate formation permeability prediction using well log data | |
| CN106526697A (en) | Method for identifying main transform plane of delta construction and destruction | |
| Emujakporue | Petrophysical properties distribution modelling of an onshore field, Niger Delta, Nigeria | |
| Wylie Jr et al. | Log-curve amplitude slicing: Visualization of log data and depositional trends in the Middle Devonian Traverse Group, Michigan basin, United States | |
| Qi et al. | Correlation of seismic attributes and geomechanical properties to the rate of penetration in the Mississippian Limestone, Oklahoma | |
| Amanipoor | Static modeling of the reservoir for estimate oil in place using the geostatistical method | |
| Flood et al. | Analysis of floodplain sedimentation, avulsion style and channelized fluvial sandbody distribution in an upper coastal plain reservoir: Middle Jurassic Ness Formation, Brent Field, UK North Sea | |
| Fajana | Hydrocarbon reservoir characterization using multi-point stochastic inversion technique: a case study of Pennay field | |
| Taura et al. | Structural and petrophysical controls on the remaining fluid distribution in the reservoirs of Gharif Formation before abandonment | |
| Li et al. | Three-dimensional reservoir architecture modeling by geostatistical techniques in BD block, Jinhu depression, northern Jiangsu Basin, China | |
| Chapin et al. | Integrated static and dynamic modeling of the Pinedale tight gas field, Wyoming | |
| Correia | Integration of reservoir characterization with history matching guided by pilot wells: Application to the Norne Field | |
| Poursamad et al. | Reservoir Quality Evaluation of Sarvak Formation in Gachsaran Oil Field, SW of Iran | |
| Akpan et al. | Utilizing Probabilistic Neural Network for Reservoir Assessment: A Case Study from an Onshore Niger Delta Field | |
| Airen et al. | Reservoir Hydrocarbon Volumetric Analysis of Sapele Deep Field, Niger Delta, Southern Nigeria | |
| Habib et al. | INTEGRATED PETROLEUM RESERVOIR CHARACTERIZATION. THE CASE OF ZHAO57 BLOCK (Es4+ EK1) | |
| Hamdulla et al. | Building geological model for tertiary reservoir of exploration Ismail oil field, North Iraq |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170905 |
|
| RJ01 | Rejection of invention patent application after publication |